Announcing Gemini 2.5 Flash Image! (Nano Banana) from Google DeepMind. This model brings you state of the art image generation! Here's 7m of demos. Today marks a leap forward in AI-powered image creativity with the launch of stronger native image generation and editing in Gemini 2.5 Flash. Here's what's... new: 👤 Consistent character design: Maintain a character's identity across multiple images, changing their outfits, poses, and scenes without losing their core look. 🎨 Creative composition: Seamlessly merge elements from up to three different images into a single, cohesive masterpiece. The potential for surrealist art and unique compositions is endless. ✍️ Targeted edits with natural language: Go beyond the prompt. You can now make highly specific edits like "change the background," "restore this faded photo," or "edit the character's outfit" with simple commands. ✨ Design & identity adaptation: Apply a specific style, texture, or pattern from one image to another, unlocking new possibilities for fashion, product design, and architectural visualization. I've put together a ~7-minute video demo to walk you through these features and show just how powerful they are in action. We can't wait to see what you all create! Try the model out in Google AI Studio, Gemini app or the Gemini API.show more

@GoogleDeepMind ❤️

@GoogleDeepMind Y'all are fast! 🍌🔥 <3 OpenRouter

@openrouter @GoogleDeepMind Insanely fast.

@openrouter @GoogleDeepMind The teams cooked! 🍌

@GoogleDeepMind For one moment I thought it was Richard from lost

@GoogleDeepMind I'll take that as a positive 😅

@GoogleDeepMind This model is incredible! It generates stunning images at lightning speed and its ability to produce accurate text within images is truly impressive

@GKannanDev @GoogleDeepMind Yes! Was really pleased with how well text-on-image works one-shot here!

@GoogleDeepMind i couldn't get it to work w/ google ai studio or the js genai package listmodels returned that it existed, but it would always 404 no matter what i did got it working w/ openrouter tho google def needs to work on its DX around new model releases

@GoogleDeepMind I think we're experiencing some capacity issues due to demand at the moment which are being looked at. Glad to hear that openrouter worked in the interim!

@GoogleDeepMind The character consistency is mind blowing

@GoogleDeepMind Easily my favorite image generation model atm for non-trivial edits.

@GoogleDeepMind Impressive but not life-changing! This is just another AI tool toy

@GoogleDeepMind Great examples! My mind is exploding with ideas rn

@shaun5k_ @GoogleDeepMind Thanks! Glad the ideas resonated. Can't wait to see folks try it out more!

@GoogleDeepMind Very useful. Thanks for making this!

@GoogleDeepMind Happy if it's helpful! 🍌

@GoogleDeepMind Great demos! Thanks for sharing.

@GoogleDeepMind A pleasure!

@GoogleDeepMind good for info graphic

@GoogleDeepMind

@GoogleDeepMind blonde Addy is it 🔥

@GoogleDeepMind 😅😅😅

@GoogleDeepMind do you have a prompt guide for nano banana

@GoogleDeepMind @_philschmid may know :)

@donvito @GoogleDeepMind Coming later today or tomorrow

@addyosmani @GoogleDeepMind thank you 🙏

@GoogleDeepMind Game-changing update! The leap in character consistency, creative merging, and natural language edits unlocks a whole new level of AI-powered artistry. Excited to push the limits—this is the toolkit visual creators have been waiting for. 🚀🎨 #GeminiFlash #AIArt

@GoogleDeepMind Awesome ✨

@GoogleDeepMind Wild how fast image models are evolving. Consistent character design feels like a huge unlock for creators

@GoogleDeepMind Was dreading if this could solve vton usecase as side feature/quest. For now not! for vton google-vton-preview-20250804 >> gemini-2.5-flash-image-preview-20250827

@GoogleDeepMind Really need to investigate your pronunciation of bicycle 😂

@theceoaicoach My years of growing up in Europe and now living in the US have...impacted my pronunciations a little 😅😅

I feel like your pronunciation of everything else is flawless. Don’t change it, makes you unique! Appreciate the breakdown vid.

@GoogleDeepMind 🍌

@GoogleDeepMind That's Awesome

@GoogleDeepMind Thanks can't wait to try the new 2.5 Flash Image :)

@GoogleDeepMind Let's go Nano-banana! 💪 🏴‍☠️

@GoogleDeepMind Ok, time to allow Gemini as the Image generation model

@GoogleDeepMind Looks promising. Going to try it out.

@GoogleDeepMind Woah nano banana is so crazyyy 🤩

@GoogleDeepMind They cooked with this one! More details from @OfficialLoganK in his great thread:

@GoogleDeepMind @OfficialLoganK Yes they really did

@GoogleDeepMind What an insanely useful and fast model! Just wow!

@GoogleDeepMind Sad that is too censored

@GoogleDeepMind Time is Light !

@GoogleDeepMind

@GoogleDeepMind this is fire! Can it do transparent backgrounds?

@GoogleDeepMind This release signals a shift: AI isn’t only generating images, it’s managing identity, continuity, and intent—the fundamentals of professional design

@GoogleDeepMind Bi–cycle 😱

@GoogleDeepMind Impressive advancements. Does enhanced creativity imply a shift towards more intuitive AI? This could redefine the boundaries of digital art.

@GoogleDeepMind Missed op to call it “nano nanner”